Abstract: 

WeightWatcher (WW) is an open-source, diagnostic tool for analyzing Deep Neural Networks (DNNs), without needing access to training or even testing data. It can be used to: analyze pre-trained/trained PyTorch, Keras, DNN models (Conv2D and Dense layers); monitor models, and the model layers, to see if they are over-trained or over-parameterized; predict test accuracies across different models, with or without training data; detect potential problems when compressing or fine-tuning pre-trained models; layer warning labels for over-trained, under-trained, etc; and more. We'll describe the basic ideas underlying WW, and we'll give multiple examples of how it can be used for the analysis of state-of-the-art models in computer vision, natural language processing, and other areas. More information is available at https://github.com/CalculatedContent/WeightWatcher; or just pip install weightwatcher.

Bio: 

Michael W. Mahoney is at the University of California at Berkeley in the Department of Statistics and at the International Computer Science Institute (ICSI). He is also an Amazon Scholar as well as a faculty scientist at the Lawrence Berkeley National Laboratory. He works on algorithmic and statistical aspects of modern large-scale data analysis. Much of his recent research has focused on large-scale machine learning, including randomized matrix algorithms and randomized numerical linear algebra, geometric network analysis tools for structure extraction in large informatics graphs, scalable implicit regularization methods, computational methods for neural network analysis, physics informed machine learning, and applications in genetics, astronomy, medical imaging, social network analysis, and internet data analysis. He received his PhD from Yale University with a dissertation in computational statistical mechanics, and he has worked and taught at Yale University in the mathematics department, at Yahoo Research, and at Stanford University in the mathematics department. Among other things, he is on the national advisory committee of the Statistical and Applied Mathematical Sciences Institute (SAMSI), he was on the National Research Council's Committee on the Analysis of Massive Data, he co-organized the Simons Institute's fall 2013 and 2018 programs on the foundations of data science, he ran the Park City Mathematics Institute's 2016 PCMI Summer Session on The Mathematics of Data, and he runs the biennial MMDS Workshops on Algorithms for Modern Massive Data Sets. He is the Director of the NSF/TRIPODS-funded FODA (Foundations of Data Analysis) Institute at UC Berkeley. More information is available at https://www.stat.berkeley.edu/~mmahoney/.